Influence of Event Duration on Automatic Wheeze Classification

Event-based social networks (EBSNs) connect online and offline lives. They allow online users with similar interests to get together in real life. Attendance prediction for activities in EBSNs has attracted a lot of attention and several factors have been studied. However, the prediction accuracy is not very good for some special activities, such as outdoor activities. Moreover, a very important factor, the weather, has not been well exploited. In this work, we strive to understand how the weather factor impacts activity attendance, and we explore it to improve attendance prediction from the organizer’s view. First, we classify activities into two categories: the outdoor and the indoor activities. We study the different ways that weather factors may impact these two kinds of activities. We also introduce a new factor of event duration. By integrating the above factors with user interest and user-event distance, we build a model of attendance prediction with the weather named GBT-W , based on the Gradient Boosting Tree. Furthermore, we develop a platform to help event organizers estimate the possible number of activity attendance with different settings (e.g., different weather, location) to effectively plan their events. We conduct extensive experiments, and the results show that our method has a better prediction performance on both the outdoor and the indoor activities, which validates the reasonability of considering weather and duration.

Download Full-text

Statistical Analysis and Machine Learning Prediction of Fog-Caused Low-Visibility Events at A-8 Motor-Road in Spain

Atmosphere ◽

10.3390/atmos12060679 ◽

2021 ◽

Vol 12 (6) ◽

pp. 679

Author(s):

Sara Cornejo-Bueno ◽

David Casillas-Pérez ◽

Laura Cornejo-Bueno ◽

Mihaela I. Chidean ◽

Antonio J. Caamaño ◽

...

Keyword(s):

Statistical Analysis ◽

Probability Distributions ◽

Pearson Correlation ◽

Likelihood Method ◽

Neural Network Approach ◽

Event Duration ◽

Full Characterization ◽

Low Visibility ◽

Learning Machine ◽

The Impact

This work presents a full statistical analysis and accurate prediction of low-visibility events due to fog, at the A-8 motor-road in Mondoñedo (Galicia, Spain). The present analysis covers two years of study, considering visibility time series and exogenous variables collected in the zone affected the most by extreme low-visibility events. This paper has then a two-fold objective: first, we carry out a statistical analysis for estimating the fittest probability distributions to the fog event duration, using the Maximum Likelihood method and an alternative method known as the L-moments method. This statistical study allows association of the low-visibility depth with the event duration, showing a clear relationship, which can be modeled with distributions for extremes such as Generalized Extreme Value and Generalized Pareto distributions. Second, we apply a neural network approach, trained by means of the ELM (Extreme Learning Machine) algorithm, to predict the occurrence of low-visibility events due to fog, from atmospheric predictive variables. This study provides a full characterization of fog events at this motor-road, in which orographic fog is predominant, causing important traffic problems during all year. We also show how the ELM approach is able to obtain highly accurate low-visibility events predictions, with a Pearson correlation coefficient of 0.8, within a half-hour time horizon, enough to initialize some protocols aiming at reducing the impact of these extreme events in the traffic of the A-8 motor road.

Download Full-text

Earth Terminal-to-Satellite Link Availability using New Rain Event Duration Statistics

10.1109/milcom.1983.4794756 ◽

1983 ◽

Author(s):

D. L. Zimmerman ◽

M. J. Riccio ◽

J. M. Ruddy

Keyword(s):

Rain Event ◽

Event Duration ◽

Satellite Link ◽

Link Availability

Download Full-text

PSVI-20 Extent of genetic variation in feeding behavior and genetic associations with performance and feed efficiency in crossbred growing cattle

Journal of Animal Science ◽

10.1093/jas/skab235.427 ◽

2021 ◽

Vol 99 (Supplement_3) ◽

pp. 233-234

Author(s):

David N Kelly ◽

Roy D Sleator ◽

Craig P Murphy ◽

Stephen B Conroy ◽

Donagh P Berry

Keyword(s):

Genetic Variation ◽

Feeding Behavior ◽

Energy Intake ◽

Feed Efficiency ◽

Fixed Effects ◽

Feeding Rate ◽

Feeding Time ◽

Genetic Associations ◽

Event Duration ◽

Growing Cattle

Abstract To the best of our knowledge, the genetic variability in feeding behavior, as well as relationships with performance and feed efficiency, has not been investigated in a cattle population of greater than 1,500 animals. Our objective was to quantify the genetic parameters of several feeding behavior traits, and their genetic associations with both performance and feed efficiency traits, in crossbred growing cattle. Feed intake and live-weight data were available on 6,088 bulls, steers and heifers; of these, 4,672 cattle had backfat and muscle ultrasound data, and 1,548 steers and heifers had feeding behavior data. Genetic (co)variance parameters were estimated using animal linear mixed models; fixed effects included test group, heterosis, recombination loss, dam parity, age in months at the end of test, and the two-way interaction between age in months at the end of test and sex. Heritability was estimated to be 0.51 (0.097), 0.61 (0.100), 0.44 (0.093), 0.48 (0.094), and 0.47 (0.095) for feed events per day, feeding time per day, feeding rate, feed event duration, and energy intake per feed event, respectively. Coefficients of genetic variation ranged from 0.11 (feeding time per day) to 0.22 (feed event duration). Genetically heavier cattle with a higher energy intake per day, and faster growth rate, had a faster feeding rate and a greater energy intake per feed event. Genetic correlations between feeding behavior and feed efficiency were generally not different from zero, however, there was a genetic correlation of 0.36 (0.11) between feeding time per day and residual energy intake. Significant heritable and exploitable genetic variation exists in several feeding behavior traits in crossbred growing cattle which are also correlated with several performance traits. As some feeding behavior traits may be relatively less resource intensive to measure, they could be useful as predictor traits in beef cattle genetic evaluations.

Download Full-text

Nondissipative and Dissipative Momentum Deposition by Mountain Wave Events in Sheared Environments

Journal of the Atmospheric Sciences ◽

10.1175/jas-d-17-0350.1 ◽

2018 ◽

Vol 75 (8) ◽

pp. 2721-2740 ◽

Cited By ~ 3

Author(s):

Christopher G. Kruse ◽

Ronald B. Smith

Keyword(s):

Broad Spectrum ◽

Numerical Models ◽

Wrf Model ◽

Vertical Wind Shear ◽

Mountain Wave ◽

Subsequent Evolution ◽

Event Duration ◽

Mountain Waves ◽

Vertical Dispersion ◽

Nonlinear Transient

AbstractMountain waves (MWs) are generated during episodic cross-barrier flow over broad-spectrum terrain. However, most MW drag parameterizations neglect transient, broad-spectrum dynamics. Here, the influences of these dynamics on both nondissipative and dissipative momentum deposition by MW events are quantified in a 2D, horizontally periodic idealized framework. The influences of the MW spectrum, vertical wind shear, and forcing duration are investigated. MW events are studied using three numerical models—the nonlinear, transient WRF Model; a linear, quasi-transient Fourier-ray model; and an optimally tuned Lindzen-type saturation parameterization—allowing quantification of total, nondissipative, and dissipative MW-induced decelerations, respectively. Additionally, a pseudomomentum diagnostic is used to estimate nondissipative decelerations within the WRF solutions. For broad-spectrum MWs, vertical dispersion controls spectrum evolution aloft. Short MWs propagate upward quickly and break first at the highest altitudes. Subsequently, the arrival of additional longer MWs allows breaking at lower altitudes because of their greater contribution to u variance. As a result, minimum breaking levels descend with time and event duration. In zero- and positive-shear environments, this descent is not smooth but proceeds downward in steps as a result of vertically recurring steepening levels. Nondissipative decelerations are nonnegligible and influence an MW’s approach to breaking, but breaking and dissipative decelerations quickly develop and dominate the subsequent evolution. Comparison of the three model solutions suggests that the conventional instant propagation and monochromatic parameterization assumptions lead to too much MW drag at too low an altitude.

Download Full-text

Movement-induced heart rate changes in epileptic and non-epileptic seizures

Arquivos de Neuro-Psiquiatria ◽

10.1590/s0004-282x2009000500001 ◽

2009 ◽

Vol 67 (3b) ◽

pp. 789-791 ◽

Cited By ~ 6

Author(s):

Gisele R. de Oliveira ◽

Francisco de A.A. Gondim ◽

Edward R. Hogan ◽

Francisco H. Rola

Keyword(s):

Heart Rate ◽

Motor Activity ◽

Rate Increase ◽

Epileptic Seizures ◽

Baseline Heart Rate ◽

Heart Rate Increase ◽

Event Duration ◽

Rate Analysis ◽

Heart Rate Analysis ◽

Video Eeg

Heart rate changes are common in epileptic and non-epileptic seizures. Previous studies have not adequately assessed the contribution of motor activity on these changes nor have evaluated them during prolonged monitoring. We retrospectively evaluated 143 seizures and auras from 76 patients admitted for video EEG monitoring. The events were classified according to the degree of ictal motor activity (severe, moderate and mild/absent) in: severe epileptic (SE, N=17), severe non-epileptic (SNE, N=6), moderate epileptic (ME, N=28), moderate non-epileptic (MNE, N=11), mild epileptic (mE, N=35), mild non-epileptic (mNE, N=33) and mild aura (aura, N=13). Heart rate increased in the ictal period in severe epileptic, severe non-epileptic, moderate epileptic and mild epileptic events (p<0.05). Heart rate returned to baseline levels during the post ictal phase in severe non-epileptic seizures but not in severe epileptic patients. Aura events had a higher baseline heart rate. A cut-off of 20% heart rate increase may distinguish moderate epileptic and mild epileptic events lasting more than 30 seconds. In epileptic seizures with mild/absent motor activity, the magnitude of heart rate increase is proportional to the event duration. Heart rate analysis in seizures with different degrees of movement during the ictal phase can help to distinguish epileptic from non-epileptic events.

Download Full-text